Statistics Exam Terms

An object (person, thing, event, transaction, etc.) upon which we collect data

A set of units (usually people, objects, transactions, or events) that we are interested in studying

A subset of the units of a population

A summary measure (i.e., an average, a proportion, etc.) that reflects the entire population

Summary measure is determined using the data collected from the sample

All people in the U.S. (each person is an experimental unit)

All U.S. males age 18-35

All sales made by the ND Bookstore last week

A characteristic or property of an individual unit. Often notated with capital letters such as X or Y.

What is your eye color?

How much cash do you have on you?

Do you suffer from diabetes

Data collected on non-numerical variables. Can be expressed in words

Data collected on numerical variables, Can be mathematically summarized

No “order” exists for the categories

The values can be ordered (arranged from lowest to highest)

Can list the possible values and the pattern of values (i.e., integers)

The possible values can be any value in a range, with any number of decimal places

Includes government agencies such as the U.S. Census and Bureau of Labor Statistics, newspapers, academic journals, universities, and websites

The researcher actively imposes a treatment on the sample units.

The researcher does not actively impose treatment on the experimental units, but records the values of the variable of interest.

A researcher can also conduct surveys via mail, telephone, e-mail, or in-person interviews

A sample selected from the population in such a way that every sample of size n has an equal chance of selection

This results when some subset of the experimental units in the population is excluded so that these units have no chance of being selected in the sample

This occurs when the researcher conducting the survey or study are unable to obtain data on all experimental units selected for the sample.

This refers to inaccuracies in the values of the data recorded. Errors may be due to ambiguous or leading questions.

A planned operation carried out under controlled conditions

A single result of an experiment

The set of all possible outcomes

One or more of the outcomes

The predicted chance (or long-term relative frequency) of an event.

values between 0 and 1, inclusive: 0<or equal P(A) < or equal 1

1

All outcomes are assumed equally likely

Probabilities are based on results of a random sample

An expert provides the probabilities

the group of outcomes in both A and B

the group of outcomes in A or B (or both)

the group of outcomes NOT in A

A occurs given that B i s known to occur

A and B have no overlap

Knowing that A has occurred does not affect the probability ofB (and vice-versa).

Events that cannot occur at the same time.

Provides a way of portraying data that can facilitate calculating probabilities

A special type of graph is used to determine the outcomes of an experiment

A picture that represents the outcome of an experiment. Generally consists of a box that represents the sample space S together with circles or ovals

A numerical description of the outcome of an experiment.

The possible values are distinct, predictable, and can be listed. The number of values can be either finite or infinite. Probabilities can be assigned to each value, but they might not be equal.

The possible values cannot be listed individually since the variables can take on any value in a range. It is not possible to list every distinct value. The number of values is always infinite and the probability of any specific value is zero.

A table, graph, or formula that specifies the probability associated with each possible value that the random variable can assume

0< or equal p(x) < or equal 1 , for all x

All x p(x) =1 , where the summation of P(x) is over all possible values of x

1. The experment consists of n identical trials

2. There are only 2 possible outcomes on each trial. We denote one outcome by S (or 1) for success, and F (or 0) for failure.

3. The probability of success is constant from trial to trial. This probability is denoted by p, and the probability of failure is

q= 1-p

4. The trials are independent → The binomial random variable x represents number of successes in n trials

only has one peak in the distribution

has two peaks in the distribution

a multimodal distribution is a probability distribution with more than one mode

the number of observations in a data set falling in a particular category

frequency divided by the total number of observations in the data set.

the number of data observations

class relative frequency multiplied by 100